src/construct/character_escape.rs


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86

//! Character escapes occur in the [string][] and [text][] content types.
//!
//! ## Grammar
//!
//! Character escapes form with the following BNF
//! (<small>see [construct][crate::construct] for character groups</small>):
//!
//! ```bnf
//! character_escape ::= '\\' ascii_punctuation
//! ```
//!
//! Like much of markdown, there are no “invalid” character escapes: just a
//! slash, or a slash followed by anything other than an ASCII punctuation
//! character, is exactly that: just a slash.
//!
//! To escape (almost all) arbitrary characters instead of only ASCII
//! punctuation, use a [character reference][character_reference] instead
//! (as in, `&amp;`, `&#123;`, or say `&#x9;`).
//!
//! It is also possible to escape a line ending in text with a similar
//! construct: a [hard break (escape)][hard_break_escape] is a backslash followed
//! by a line ending (that is part of the construct instead of ending it).
//!
//! ## Recommendation
//!
//! If possible, use a character escape.
//! Otherwise, use a character reference.
//!
//! ## Tokens
//!
//! *   [`CharacterEscape`][Name::CharacterEscape]
//! *   [`CharacterEscapeMarker`][Name::CharacterEscapeMarker]
//! *   [`CharacterEscapeValue`][Name::CharacterEscapeValue]
//!
//! ## References
//!
//! *   [`character-escape.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/character-escape.js)
//! *   [*§ 2.4 Backslash escapes* in `CommonMark`](https://spec.commonmark.org/0.30/#backslash-escapes)
//!
//! [string]: crate::construct::string
//! [text]: crate::construct::text
//! [character_reference]: crate::construct::character_reference
//! [hard_break_escape]: crate::construct::hard_break_escape

use crate::event::Name;
use crate::state::{Name as StateName, State};
use crate::tokenizer::Tokenizer;

/// Start of character escape.
///
/// ```markdown
/// > | a\*b
///      ^
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
    if tokenizer.parse_state.options.constructs.character_escape && tokenizer.current == Some(b'\\')
    {
        tokenizer.enter(Name::CharacterEscape);
        tokenizer.enter(Name::CharacterEscapeMarker);
        tokenizer.consume();
        tokenizer.exit(Name::CharacterEscapeMarker);
        State::Next(StateName::CharacterEscapeInside)
    } else {
        State::Nok
    }
}

/// After `\`, at punctuation.
///
/// ```markdown
/// > | a\*b
///       ^
/// ```
pub fn inside(tokenizer: &mut Tokenizer) -> State {
    match tokenizer.current {
        // ASCII punctuation.
        Some(b'!'..=b'/' | b':'..=b'@' | b'['..=b'`' | b'{'..=b'~') => {
            tokenizer.enter(Name::CharacterEscapeValue);
            tokenizer.consume();
            tokenizer.exit(Name::CharacterEscapeValue);
            tokenizer.exit(Name::CharacterEscape);
            State::Ok
        }
        _ => State::Nok,
    }
}